Sequential Monte Carlo computation of the score and observed information matrix in state-space models with application to parameter estimation

Sequential Monte Carlo (SMC) methods are popular computational tools for Bayesian inference in non-linear non-Gaussian state-space models. For this class of models, we propose SMC algorithms to compute the score vector and observed information matrix recursively in time. We propose two different SMC implementations, one with computational complexity $\mathcal{O}(N)$ and the other with complexity $\mathcal{O}(N^{2})$ where $N$ is the number of importance sampling draws. Although cheaper, the performance of the $\mathcal{O}(N)$ method degrades quickly in time as it inherently relies on the SMC approximation of a sequence of probability distributions whose dimension is increasing linearly with time. In particular, even under strong \textit{mixing} assumptions, the variance of the estimates computed with the $\mathcal{O}(N)$ method increases at least quadratically in time. The $\mathcal{O}(N^{2})$ is a non-standard SMC implementation that does not suffer from this rapid degrade. We then show how both methods can be used to perform batch and recursive parameter estimation.

Algorithms for colour image processing based on neurological models

373 p. : il., gráf., fot., tablas

Efficient learning of decomposable models with a bounded clique size

The learning of probability distributions from data is a ubiquitous problem in the fields of Statistics and Artificial Intelligence. During the last decades several learning algorithms have been proposed to learn probability distributions based on decomposable models due to their advantageous theoretical properties. Some of these algorithms can be used to search for a maximum likelihood decomposable model with a given maximum clique size, k, which controls the complexity of the model. Unfortunately, the problem of learning a maximum likelihood decomposable model given a maximum clique size is NP-hard for k > 2. In this work, we propose a family of algorithms which approximates this problem with a computational complexity of O(k · n^2 log n) in the worst case, where n is the number of implied random variables. The structures of the decomposable models that solve the maximum likelihood problem are called maximal k-order decomposable graphs. Our proposals, called fractal trees, construct a sequence of maximal i-order decomposable graphs, for i = 2, ..., k, in k − 1 steps. At each step, the algorithms follow a divide-and-conquer strategy based on the particular features of this type of structures. Additionally, we propose a prune-and-graft procedure which transforms a maximal k-order decomposable graph into another one, increasing its likelihood. We have implemented two particular fractal tree algorithms called parallel fractal tree and sequential fractal tree. These algorithms can be considered a natural extension of Chow and Liu’s algorithm, from k = 2 to arbitrary values of k. Both algorithms have been compared against other efficient approaches in artificial and real domains, and they have shown a competitive behavior to deal with the maximum likelihood problem. Due to their low computational complexity they are especially recommended to deal with high dimensional domains.

Computational modeling and psychophysics in low- and mid-level vision

This thesis addresses a series of topics related to the question of how people find the foreground objects from complex scenes. With both computer vision modeling, as well as psychophysical analyses, we explore the computational principles for low- and mid-level vision.

We first explore the computational methods of generating saliency maps from images and image sequences. We propose an extremely fast algorithm called Image Signature that detects the locations in the image that attract human eye gazes. With a series of experimental validations based on human behavioral data collected from various psychophysical experiments, we conclude that the Image Signature and its spatial-temporal extension, the Phase Discrepancy, are among the most accurate algorithms for saliency detection under various conditions.

In the second part, we bridge the gap between fixation prediction and salient object segmentation with two efforts. First, we propose a new dataset that contains both fixation and object segmentation information. By simultaneously presenting the two types of human data in the same dataset, we are able to analyze their intrinsic connection, as well as understanding the drawbacks of today’s “standard” but inappropriately labeled salient object segmentation dataset. Second, we also propose an algorithm of salient object segmentation. Based on our novel discoveries on the connections of fixation data and salient object segmentation data, our model significantly outperforms all existing models on all 3 datasets with large margins.

In the third part of the thesis, we discuss topics around the human factors of boundary analysis. Closely related to salient object segmentation, boundary analysis focuses on delimiting the local contours of an object. We identify the potential pitfalls of algorithm evaluation for the problem of boundary detection. Our analysis indicates that today’s popular boundary detection datasets contain significant level of noise, which may severely influence the benchmarking results. To give further insights on the labeling process, we propose a model to characterize the principles of the human factors during the labeling process.

The analyses reported in this thesis offer new perspectives to a series of interrelating issues in low- and mid-level vision. It gives warning signs to some of today’s “standard” procedures, while proposing new directions to encourage future research.

An extended computational model of the circulatory system for designing ventricular assist devices.

An extended computational model of the circulatory system has been developed to predict blood flow in the presence of ventricular assist devices (VADs). A novel VAD, placed in the descending aorta, intended to offload the left ventricle (LV) and augment renal perfusion is being studied. For this application, a better understanding of the global hemodynamic response of the VAD, in essence an electrically driven pump, and the cardiovascular system is necessary. To meet this need, a model has been established as a nonlinear, lumped-parameter electrical analog, and simulated results under different states [healthy, congestive heart failure (CHF), and postinsertion of VAD] are presented. The systemic circulation is separated into five compartments and the descending aorta is composed of three components to accurately yield the system response of each section before and after the insertion of the VAD. Delays in valve closing time and blood inertia in the aorta were introduced to deliver a more realistic model. Pump governing equations and optimization are based on fundamental theories of turbomachines and can serve as a practical initial design point for rotary blood pumps. The model's results closely mimic established parameters for the circulatory system and confirm the feasibility of the intra-aortic VAD concept. This computational model can be linked with models of the pump motor to provide a valuable tool for innovative VAD design.

Internal models in the cerebellum.

This review will focus on the possibility that the cerebellum contains an internal model or models of the motor apparatus. Inverse internal models can provide the neural command necessary to achieve some desired trajectory. First, we review the necessity of such a model and the evidence, based on the ocular following response, that inverse models are found within the cerebellar circuitry. Forward internal models predict the consequences of actions and can be used to overcome time delays associated with feedback control. Secondly, we review the evidence that the cerebellum generates predictions using such a forward model. Finally, we review a computational model that includes multiple paired forward and inverse models and show how such an arrangement can be advantageous for motor learning and control.

Computational approaches to motor control.

This review will focus on four areas of motor control which have recently been enriched both by neural network and control system models: motor planning, motor prediction, state estimation and motor learning. We will review the computational foundations of each of these concepts and present specific models which have been tested by psychophysical experiments. We will cover the topics of optimal control for motor planning, forward models for motor prediction, observer models of state estimation arid modular decomposition in motor learning. The aim of this review is to demonstrate how computational approaches, as well as proposing specific models, provide a theoretical framework to formalize the issues in motor control.